An Efficient Medical Image Deep Fusion Model Based on Convolutional Neural Networks

Medical image fusion is considered the best method for obtaining one image with rich details for efficient medical diagnosis and therapy. Deep learning provides a high performance for several medical image analysis applications. This paper proposes a deep learning model for the medical image fusion process. This model depends on Convolutional Neural Network (CNN). The basic idea of the proposed model is to extract features from both CT and MR images. Then, an additional process is executed on the extracted features. After that, the fused feature map is reconstructed to obtain the resulting fused image. Finally, the quality of the resulting fused image is enhanced by various enhancement techniques such as Histogram Matching (HM), Histogram Equalization (HE), fuzzy technique, fuzzy type Π, and Contrast Limited Histogram Equalization (CLAHE). The performance of the proposed fusion-based CNN model is measured by various metrics of the fusion and enhancement quality. Different realistic datasets of different modalities and diseases are tested and implemented. Also, real datasets are tested in the simulation analysis.     

Real-time quality authentication of honey using atmospheric pressure chemical ionisation mass spectrometry (APCI-MS)

The aim of this study was to use gas chromatography-mass spectrometry (GC-MS) and APCI-MS techniques to detect adulteration in honey. The key volatile compounds in the headspace of the adulterated honey were marked by GC-MS and their representative fragment ions were utilised in scanning honey samples using the real-time APCI-MS system. The PLS models validated using independent data sets resulted in coefficient of the determination () of 0.97 and 0.96 and root mean square error in prediction (RMSEP) of 2.62 and 2.45 for the GC-MS and APCI-MS data sets respectively. The most efficient volatiles from GC-MS analysis and their corresponding fragment ions m/z from APCI-MS data analysis were then identified and used to develop new PLS models to predict the level of adulteration. The best PLS model gave of 0.95 and RMEP of 2.60% in the independent validation set indicating that the model was very accurate in predicting the level of adulteration.     

The finite-element deformation modeling of superplastic Al-8090

The deformation behaviors of an Al-Li-Cu alloy (Aluminum 8090) during uniaxial and biaxial stress states were modeled using the nonlinear finite element analysis package ABAQUS 5.8. Two different material models were used for the purpose of comparison and to propose a valid and accurate superplastic material deformation behavior. Using a power law strain hardening model, the material was modeled with either constant or variable properties of strain-rate sensitivity and strain-hardening exponent. Results from the numerical models were compared to experimental results by Chen and Huang, who investigated the uniaxial and biaxial states of stress. Experimental data were primarily used to acquire the needed uniaxial material parameters for the model. The strain-rate sensitivity and strain-hardening exponent were dependent on the strain and strain rates. Comparing the two material models for both stress states indicated that the material model with variable properties better represented the true behavior of the material when compared to the experimental results. For more information, contact Noha M. Hassan, the American University in Cairo, 113 Kasr El Aini St., P.O. Box 2511, Cairo 11511, Egypt; +202-797-5336; fax +202-797-7565; e-mail nhassan@vt.edu.     

Classification by ensembles from random partitions of high-dimensional data

A robust classification procedure is developed based on ensembles of classifiers, with each classifier constructed from a different set of predictors determined by a random partition of the entire set of predictors. The proposed methods combine the results of multiple classifiers to achieve a substantially improved prediction compared to the optimal single classifier. This approach is designed specifically for high-dimensional data sets for which a classifier is sought. By combining classifiers built from each subspace of the predictors, the proposed methods achieve a computational advantage in tackling the growing problem of dimensionality. For each subspace of the predictors, we build a classification tree or logistic regression tree. Our study shows, using four real data sets from different areas, that our methods perform consistently well compared to widely used classification methods. For unbalanced data, our approach maintains the balance between sensitivity and specificity more adequately than many other classification methods considered in this study.     

A constraint consensus memetic algorithm for solving constrained optimization problems

Constraint handling is an important aspect of evolutionary constrained optimization. Currently, the mechanism used for constraint handling with evolutionary algorithms mainly assists the selection process, but not the actual search process. In this article, first a genetic algorithm is combined with a class of search methods, known as constraint consensus methods, that assist infeasible individuals to move towards the feasible region. This approach is also integrated with a memetic algorithm. The proposed algorithm is tested and analysed by solving two sets of standard benchmark problems, and the results are compared with other state-of-the-art algorithms. The comparisons show that the proposed algorithm outperforms other similar algorithms. The algorithm has also been applied to solve a practical economic load dispatch problem, where it also shows superior performance over other algorithms.     

Synthesis and applications of some new antioxidant and anticorrosive additives for Egyptian diesel motor oils

Pyrimidine‐5‐carboxylate derivative Ia was utilised as a key intermediate for the synthesis of new pyrimidine derivatives. Thiopyrimidine derivative Ia undergo N‐methylation using methyl iodide afforded III. Methylsulfanyl moiety in II was easily removed when reacted with phenyl hydrazine and thiosemicarbazide afforded pyrimidine derivatives IV and VI, respectively. The reaction on nitrogen atom in Ia using 1,3‐dibromo‐propane, benzoyl chloride, phosphorous oxychloride afforded VIII, IX and X, respectively. The reaction using 1,3‐dibromo‐propane or 1,2‐dibromo‐ethane furnished the formation of the corresponding fused cycles containing sulfur. Representative compounds of the synthesised products were evaluated as antioxidant and corrosion inhibitors for gasoline lube oils. Copyright © 2010 John Wiley & Sons, Ltd.     

Non-oxidative Decomposition of CH4 Over CeO2 and CeO2–SiO2 Supported Bimetallic Ni–Mo Catalysts

Catalysis Letters - The development of highly active and durable catalysts for H2 production through CH4 decomposition process is still a great challenge. In this study, CeO2 and CeO2–SiO2...     

Dual growth of graphene nanoplatelets and carbon nanotubes hybrid structure via chemical vapor deposition of methane over Fe–MgO catalysts

Abstract

In this study, Fe–MgO catalyst substrates with various Fe and MgO combinations were evaluated for the growth of different types of carbon nanostructure materials (CNMs), particularly graphene nanoplatelets (GNPs) and carbon nanotubes (CNTs) via chemical vapor deposition using methane as a carbon source. The hydrogen yield was also determined as a valuable by-product in this process. Therefore, a set of Fe–MgO catalysts with different iron loadings (30, 80, 85, 90 and 100?wt %) were prepared by the combustion method to realize this target. The physicochemical properties of freshly calcined Fe–MgO catalysts were investigated by XRD, TPR and BET, while the as-grown CNMs were studied by HR-TEM, XRD and Raman spectroscopy. The results verified that the morphology of as-grown CNMs as well as the H₂ yield was directly correlated to the iron content in the catalyst composition. The XRD and TPR results showed that various FeMgO_x species with deferent levels of interactions were produced with the gradual incorporation of MgO content. TEM images indicated that GNPs were individually grown on the surface of high loaded iron-containing catalysts (90–100?wt %) due to the presence of highly aggregated iron particles. While multi-walled carbon nanotubes (MWCNTs) with uniform diameters were grown on the low iron-loaded catalyst (30%Fe/MgO) due to the formation of highly dispersed FeMgO_x particles. On the other hand, GNPs/MWCNTs hybrid materials were grown on the surface of 80%Fe and 85%Fe/MgO catalysts. This behavior can be interpreted by the co-existence of highly aggregated and highly dispersed Fe₂O₃ particles in the catalyst matrix. The results demonstrated that the catalyst composition has a notable effect on the nature of CNMs products and H₂ yield.